Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Id/UserId

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ぬ
    -0.07
     drop
    -0.07
    letion
    -0.07
    uch
    -0.07
     enact
    -0.07
     כגון
    -0.06
     Gordon
    -0.06
     ranger
    -0.06
     give
    -0.06
    语
    -0.06
    POSITIVE LOGITS
    🌈
    0.08
     roofs
    0.08
    อาจาร
    0.07
    宝藏
    0.07
     StyleSheet
    0.07
    🚗
    0.07
     unterstüt
    0.07
    ฝน
    0.07
     безопас
    0.07
    𝘍
    0.07
    Act Density 0.042%

    No Known Activations